StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics

TL;DR

StoryBlender is a novel 3D storyboard generation framework that ensures inter-shot consistency and explicit editability by combining semantic grounding, unified asset instantiation, and dynamic layout design.

Contribution

It introduces a three-stage pipeline with a hierarchical agent system that self-corrects spatial hallucinations, enabling native 3D scenes with improved consistency and editability.

Findings

Significantly improves multi-shot consistency over baselines.

Supports direct, precise editing of cameras and assets.

Demonstrates effective long-horizon cinematic scene generation.

Abstract

Storyboarding is a core skill in visual storytelling for film, animation, and games. However, automating this process requires a system to achieve two properties that current approaches rarely satisfy simultaneously: inter-shot consistency and explicit editability. While 2D diffusion-based generators produce vivid imagery, they often suffer from identity drift along with limited geometric control; conversely, traditional 3D animation workflows are consistent and editable but require expert-heavy, labor-intensive authoring. We present StoryBlender, a grounded 3D storyboard generation framework governed by a Story-centric Reflection Scheme. At its core, we propose the StoryBlender system, which is built on a three-stage pipeline: (1) Semantic-Spatial Grounding, to construct a continuity memory graph to decouple global assets from shot-specific variables for long-horizon consistency; (2) Canonical Asset Materialization, to instantiate entities in a unified coordinate space to maintain visual identity; and (3) Spatial-Temporal Dynamics, to achieve layout design and cinematic evolution through visual metrics. By orchestrating multiple agents in a hierarchical manner within a verification loop, StoryBlender iteratively self-corrects spatial hallucinations via engine-verified feedback. The resulting native 3D scenes support direct, precise editing of cameras and visual assets while preserving unwavering multi-shot continuity. Experiments demonstrate that StoryBlender significantly improves consistency and editability over both diffusion-based and 3D-grounded baselines. Code, data, and demonstration video will be available on https://engineeringai-lab.github.io/StoryBlender/